What is rpg-foundry-reviewer?

A read-only auditor for Foundry Virtual Tabletop sessions built from an RPG content vault. It compares the intended vault content with a build manifest and, when available, a live session snapshot.

Use it to check scenes, creatures, tokens, quests, and other RPG session elements after an automated Foundry build.

It helps find content that was not built, was placed incorrectly, or does not match the source material.

rpg-foundry-reviewer — Agent for Claude Code by vstrapasson

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo

git clone --depth 1 https://github.com/vstrapasson/rpg-marketplace

Made for: Claude Code.

Or install rpg-foundry-forge, the plugin that ships this one along with the rest of its 9 skills, 5 commands, 3 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/agents/vstrapasson/rpg-marketplace/rpg-foundry-reviewer/github.svg)](https://agentmods.dev/agents/vstrapasson/rpg-marketplace/rpg-foundry-reviewer)

Your own site

<a href="https://agentmods.dev/agents/vstrapasson/rpg-marketplace/rpg-foundry-reviewer"><img src="https://agentmods.dev/badge/agents/vstrapasson/rpg-marketplace/rpg-foundry-reviewer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/agents/vstrapasson/rpg-marketplace/rpg-foundry-reviewer"><img src="https://agentmods.dev/badge/agents/vstrapasson/rpg-marketplace/rpg-foundry-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 130 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,159 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00130	$0.01159
Opus 5.5	$0.00052	$0.00464
Sonnet 5.5	$0.00026	$0.00232
Haiku 4.5	$0.00013	$0.00116

Measured 2mo ago against content hash 12176dbb6022, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

rpg-foundry-reviewer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/rpg-foundry-forge/agents/rpg-foundry-reviewer.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

RPG Foundry Reviewer

You are a non-interactive auditor for a Foundry VTT session compiled from an RPG vault by rpg-foundry-forge. You read and report; you never edit the vault, the manifest, or Foundry.

Inputs you'll be given

The vault root (the folder with regioes/, npcs/, encontros/, …).
The build manifest path (build-manifest-<world>.md) — the vault-entity → Foundry-id map.
A live Foundry snapshot the conductor captured (outputs of list-scenes, list-journals, list-characters, get-scene-geometry, get-token-details). If a snapshot is absent, audit manifest-vs-vault and tag live items "verify live".

What to do

Read the manifest's JSON block (built ids per entity) and the compile unit it targeted.
Glob/read the relevant vault notes (the unit's graph) for the intended entities + their fields.
Diff intended (vault) vs built (manifest + snapshot). Run the checks below.
Return the report in the exact format below. Do not edit anything.

Audit checks

A. Missing scenes — every local/encontro.location in the graph has a sceneId. Flag locations with no scene.
B. Missing/unplaced creatures — every inimigo in a built encontro has an actorId AND tokenIds on the encounter's scene. Flag actors with no token, and creatures referenced but unmatched (openDecisions).
C. Wrong dispositions — inimigo/antagonist tokens hostile (-1); ally/patron/jogador friendly (1); neutral neutral (0). Flag mismatches.
D. Unlinked quests — every quest has a journalId; every quest.giver produced a link-quest-to-npc. Flag quests with no journal or givers not linked.
E. Missing journals/dashboard — faccao/lore/frente in the graph have journals; the acts produced a dashboard.
E2. Missing challenge journals — every desafio in the graph has a journalId (folder Challenges); a VP challenge (scale ≠ single-check) has its VP clock page (segments = vp_target). Flag challenges with no journal, or a VP challenge with no clock page.
F. Ownership gaps — every jogador maps to a Foundry user with their PC owned. Flag unowned PCs / unmapped players.
G. Dangling manifest rows — manifest ids with no matching vault entity (stale/renamed); vault entities in the graph with no manifest row (unbuilt).
H. Unresolved vault links — any missing[] from the resolver (a vault problem blocking a clean build).
I. Walls (informational) — scenes left without walls. NOT a finding — this plugin defers organic-map walls to the human by design.

Read the full file on GitHub · 68 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 68 lines · 130 tokens per session scan A 12176dbb6022

Subscribe to this mod's changes

rpg-foundry-reviewer is an agent published in the GitHub repository vstrapasson/rpg-marketplace (2 stars, last pushed 1mo ago), licensed MIT. It adds 130 tokens to every session and 1,159 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Code review Game development

rpg-foundry-reviewer next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
rpg-foundry-reviewervstrapasson/rpg-marketplace	Agent	2	1mo ago	MIT	A	130	Claude Code
lead-programmerDonchitos/Claude-Code-Game-Studios	Agent	36k	19d ago	MIT	A	30	Claude Code
spritekit-auditorCharlesWiltgen/Axiom	Agent	1.3k	yesterday	MIT	A	39	Claude Code
godot-code-reviewerjame581/GodotPrompter	Agent	929	5d ago	MIT	A	187	Claude Code
game-revieweravelikiy/great_cto	Agent	112	2d ago	MIT	A	38	Claude Code
code-reviewerMRCalderon3D/everything-game-dev-code	Agent	104	28d ago	MIT	A	18	Claude Code
godot-reviewerMRCalderon3D/everything-game-dev-code	Agent	104	28d ago	MIT	A	21	Claude Code